Training in progress, step 40000
Browse files- trainer_log.jsonl +42 -0
trainer_log.jsonl
CHANGED
|
@@ -8157,3 +8157,45 @@
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 4.952, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "1 day, 7:45:37", "remaining_time": "0:09:49", "throughput": 471.6, "total_tokens": 53921712}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 4.9077, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 7:45:40", "remaining_time": "0:09:34", "throughput": 471.65, "total_tokens": 53928784}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 4.496033191680908, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 7:53:46", "remaining_time": "0:09:37", "throughput": 469.66, "total_tokens": 53928784}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8157 |
{"current_steps": 39795, "total_steps": 40000, "loss": 4.952, "lr": 3.2720109079037443e-09, "epoch": 1.273766084117534, "percentage": 99.49, "elapsed_time": "1 day, 7:45:37", "remaining_time": "0:09:49", "throughput": 471.6, "total_tokens": 53921712}
|
| 8158 |
{"current_steps": 39800, "total_steps": 40000, "loss": 4.9077, "lr": 3.1151063006468193e-09, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 7:45:40", "remaining_time": "0:09:34", "throughput": 471.65, "total_tokens": 53928784}
|
| 8159 |
{"current_steps": 39800, "total_steps": 40000, "eval_loss": 4.496033191680908, "epoch": 1.2739261250880225, "percentage": 99.5, "elapsed_time": "1 day, 7:53:46", "remaining_time": "0:09:37", "throughput": 469.66, "total_tokens": 53928784}
|
| 8160 |
+
{"current_steps": 39805, "total_steps": 40000, "loss": 5.485, "lr": 2.962056527169854e-09, "epoch": 1.274086166058511, "percentage": 99.51, "elapsed_time": "1 day, 7:53:49", "remaining_time": "0:09:22", "throughput": 469.7, "total_tokens": 53935552}
|
| 8161 |
+
{"current_steps": 39810, "total_steps": 40000, "loss": 3.8043, "lr": 2.8128616110761898e-09, "epoch": 1.2742462070289995, "percentage": 99.52, "elapsed_time": "1 day, 7:53:51", "remaining_time": "0:09:08", "throughput": 469.75, "total_tokens": 53942256}
|
| 8162 |
+
{"current_steps": 39815, "total_steps": 40000, "loss": 4.4255, "lr": 2.6675215753724223e-09, "epoch": 1.274406247999488, "percentage": 99.54, "elapsed_time": "1 day, 7:53:53", "remaining_time": "0:08:53", "throughput": 469.8, "total_tokens": 53948512}
|
| 8163 |
+
{"current_steps": 39820, "total_steps": 40000, "loss": 4.6643, "lr": 2.5260364424739557e-09, "epoch": 1.2745662889699763, "percentage": 99.55, "elapsed_time": "1 day, 7:53:55", "remaining_time": "0:08:39", "throughput": 469.85, "total_tokens": 53955520}
|
| 8164 |
+
{"current_steps": 39825, "total_steps": 40000, "loss": 4.8305, "lr": 2.3884062341994475e-09, "epoch": 1.2747263299404648, "percentage": 99.56, "elapsed_time": "1 day, 7:53:58", "remaining_time": "0:08:24", "throughput": 469.9, "total_tokens": 53962352}
|
| 8165 |
+
{"current_steps": 39830, "total_steps": 40000, "loss": 4.1801, "lr": 2.25463097177081e-09, "epoch": 1.2748863709109532, "percentage": 99.58, "elapsed_time": "1 day, 7:54:00", "remaining_time": "0:08:10", "throughput": 469.95, "total_tokens": 53969264}
|
| 8166 |
+
{"current_steps": 39835, "total_steps": 40000, "loss": 3.4962, "lr": 2.1247106758215397e-09, "epoch": 1.2750464118814415, "percentage": 99.59, "elapsed_time": "1 day, 7:54:02", "remaining_time": "0:07:55", "throughput": 470.0, "total_tokens": 53976032}
|
| 8167 |
+
{"current_steps": 39840, "total_steps": 40000, "loss": 3.9358, "lr": 1.998645366382834e-09, "epoch": 1.27520645285193, "percentage": 99.6, "elapsed_time": "1 day, 7:54:04", "remaining_time": "0:07:41", "throughput": 470.05, "total_tokens": 53982976}
|
| 8168 |
+
{"current_steps": 39845, "total_steps": 40000, "loss": 4.8239, "lr": 1.876435062897475e-09, "epoch": 1.2753664938224185, "percentage": 99.61, "elapsed_time": "1 day, 7:54:06", "remaining_time": "0:07:26", "throughput": 470.11, "total_tokens": 53990112}
|
| 8169 |
+
{"current_steps": 39850, "total_steps": 40000, "loss": 4.3512, "lr": 1.758079784211497e-09, "epoch": 1.275526534792907, "percentage": 99.62, "elapsed_time": "1 day, 7:54:09", "remaining_time": "0:07:12", "throughput": 470.16, "total_tokens": 53996960}
|
| 8170 |
+
{"current_steps": 39855, "total_steps": 40000, "loss": 3.6973, "lr": 1.6435795485797434e-09, "epoch": 1.2756865757633955, "percentage": 99.64, "elapsed_time": "1 day, 7:54:11", "remaining_time": "0:06:57", "throughput": 470.21, "total_tokens": 54003616}
|
| 8171 |
+
{"current_steps": 39860, "total_steps": 40000, "loss": 4.4603, "lr": 1.5329343736547596e-09, "epoch": 1.275846616733884, "percentage": 99.65, "elapsed_time": "1 day, 7:54:13", "remaining_time": "0:06:43", "throughput": 470.25, "total_tokens": 54010320}
|
| 8172 |
+
{"current_steps": 39865, "total_steps": 40000, "loss": 3.6412, "lr": 1.4261442765006739e-09, "epoch": 1.2760066577043723, "percentage": 99.66, "elapsed_time": "1 day, 7:54:15", "remaining_time": "0:06:28", "throughput": 470.3, "total_tokens": 54016752}
|
| 8173 |
+
{"current_steps": 39870, "total_steps": 40000, "loss": 5.2725, "lr": 1.3232092735876445e-09, "epoch": 1.2761666986748608, "percentage": 99.67, "elapsed_time": "1 day, 7:54:17", "remaining_time": "0:06:14", "throughput": 470.35, "total_tokens": 54023792}
|
| 8174 |
+
{"current_steps": 39875, "total_steps": 40000, "loss": 3.5467, "lr": 1.2241293807918607e-09, "epoch": 1.2763267396453493, "percentage": 99.69, "elapsed_time": "1 day, 7:54:19", "remaining_time": "0:06:00", "throughput": 470.41, "total_tokens": 54030800}
|
| 8175 |
+
{"current_steps": 39880, "total_steps": 40000, "loss": 4.8853, "lr": 1.128904613387216e-09, "epoch": 1.2764867806158375, "percentage": 99.7, "elapsed_time": "1 day, 7:54:22", "remaining_time": "0:05:45", "throughput": 470.46, "total_tokens": 54038272}
|
| 8176 |
+
{"current_steps": 39885, "total_steps": 40000, "loss": 4.7676, "lr": 1.0375349860591853e-09, "epoch": 1.276646821586326, "percentage": 99.71, "elapsed_time": "1 day, 7:54:24", "remaining_time": "0:05:31", "throughput": 470.51, "total_tokens": 54044944}
|
| 8177 |
+
{"current_steps": 39890, "total_steps": 40000, "loss": 3.9065, "lr": 9.5002051290205e-10, "epoch": 1.2768068625568145, "percentage": 99.72, "elapsed_time": "1 day, 7:54:26", "remaining_time": "0:05:16", "throughput": 470.56, "total_tokens": 54051744}
|
| 8178 |
+
{"current_steps": 39895, "total_steps": 40000, "loss": 4.2099, "lr": 8.663612074077954e-10, "epoch": 1.276966903527303, "percentage": 99.74, "elapsed_time": "1 day, 7:54:28", "remaining_time": "0:05:02", "throughput": 470.61, "total_tokens": 54058176}
|
| 8179 |
+
{"current_steps": 39900, "total_steps": 40000, "loss": 4.1818, "lr": 7.865570824799884e-10, "epoch": 1.2771269444977915, "percentage": 99.75, "elapsed_time": "1 day, 7:54:30", "remaining_time": "0:04:47", "throughput": 470.66, "total_tokens": 54065248}
|
| 8180 |
+
{"current_steps": 39905, "total_steps": 40000, "loss": 4.4327, "lr": 7.106081504254514e-10, "epoch": 1.27728698546828, "percentage": 99.76, "elapsed_time": "1 day, 7:54:32", "remaining_time": "0:04:33", "throughput": 470.71, "total_tokens": 54071648}
|
| 8181 |
+
{"current_steps": 39910, "total_steps": 40000, "loss": 4.1104, "lr": 6.385144229570372e-10, "epoch": 1.2774470264387683, "percentage": 99.78, "elapsed_time": "1 day, 7:54:35", "remaining_time": "0:04:19", "throughput": 470.76, "total_tokens": 54078176}
|
| 8182 |
+
{"current_steps": 39915, "total_steps": 40000, "loss": 4.3922, "lr": 5.70275911190854e-10, "epoch": 1.2776070674092568, "percentage": 99.79, "elapsed_time": "1 day, 7:54:37", "remaining_time": "0:04:04", "throughput": 470.81, "total_tokens": 54084912}
|
| 8183 |
+
{"current_steps": 39920, "total_steps": 40000, "loss": 4.0688, "lr": 5.058926256490403e-10, "epoch": 1.2777671083797453, "percentage": 99.8, "elapsed_time": "1 day, 7:54:39", "remaining_time": "0:03:50", "throughput": 470.85, "total_tokens": 54091424}
|
| 8184 |
+
{"current_steps": 39925, "total_steps": 40000, "loss": 3.7378, "lr": 4.4536457626254134e-10, "epoch": 1.2779271493502335, "percentage": 99.81, "elapsed_time": "1 day, 7:54:41", "remaining_time": "0:03:35", "throughput": 470.9, "total_tokens": 54098000}
|
| 8185 |
+
{"current_steps": 39930, "total_steps": 40000, "loss": 5.0885, "lr": 3.88691772365557e-10, "epoch": 1.278087190320722, "percentage": 99.83, "elapsed_time": "1 day, 7:54:43", "remaining_time": "0:03:21", "throughput": 470.95, "total_tokens": 54104816}
|
| 8186 |
+
{"current_steps": 39935, "total_steps": 40000, "loss": 4.0524, "lr": 3.358742226955425e-10, "epoch": 1.2782472312912105, "percentage": 99.84, "elapsed_time": "1 day, 7:54:45", "remaining_time": "0:03:06", "throughput": 471.0, "total_tokens": 54111488}
|
| 8187 |
+
{"current_steps": 39940, "total_steps": 40000, "loss": 5.281, "lr": 2.8691193539875925e-10, "epoch": 1.278407272261699, "percentage": 99.85, "elapsed_time": "1 day, 7:54:47", "remaining_time": "0:02:52", "throughput": 471.05, "total_tokens": 54118352}
|
| 8188 |
+
{"current_steps": 39945, "total_steps": 40000, "loss": 4.4591, "lr": 2.418049180274995e-10, "epoch": 1.2785673132321875, "percentage": 99.86, "elapsed_time": "1 day, 7:54:50", "remaining_time": "0:02:38", "throughput": 471.1, "total_tokens": 54125232}
|
| 8189 |
+
{"current_steps": 39950, "total_steps": 40000, "loss": 4.9959, "lr": 2.005531775373104e-10, "epoch": 1.2787273542026758, "percentage": 99.88, "elapsed_time": "1 day, 7:54:52", "remaining_time": "0:02:23", "throughput": 471.15, "total_tokens": 54131792}
|
| 8190 |
+
{"current_steps": 39955, "total_steps": 40000, "loss": 4.05, "lr": 1.6315672028699435e-10, "epoch": 1.2788873951731643, "percentage": 99.89, "elapsed_time": "1 day, 7:54:54", "remaining_time": "0:02:09", "throughput": 471.2, "total_tokens": 54138736}
|
| 8191 |
+
{"current_steps": 39960, "total_steps": 40000, "loss": 4.7774, "lr": 1.2961555204693555e-10, "epoch": 1.2790474361436528, "percentage": 99.9, "elapsed_time": "1 day, 7:54:56", "remaining_time": "0:01:55", "throughput": 471.25, "total_tokens": 54145120}
|
| 8192 |
+
{"current_steps": 39965, "total_steps": 40000, "loss": 3.6987, "lr": 9.992967798799768e-11, "epoch": 1.2792074771141413, "percentage": 99.91, "elapsed_time": "1 day, 7:54:58", "remaining_time": "0:01:40", "throughput": 471.3, "total_tokens": 54151872}
|
| 8193 |
+
{"current_steps": 39970, "total_steps": 40000, "loss": 4.404, "lr": 7.409910268707521e-11, "epoch": 1.2793675180846296, "percentage": 99.92, "elapsed_time": "1 day, 7:55:00", "remaining_time": "0:01:26", "throughput": 471.35, "total_tokens": 54158800}
|
| 8194 |
+
{"current_steps": 39975, "total_steps": 40000, "loss": 3.6288, "lr": 5.212383012986877e-11, "epoch": 1.279527559055118, "percentage": 99.94, "elapsed_time": "1 day, 7:55:02", "remaining_time": "0:01:11", "throughput": 471.4, "total_tokens": 54165648}
|
| 8195 |
+
{"current_steps": 39980, "total_steps": 40000, "loss": 3.8687, "lr": 3.400386370533415e-11, "epoch": 1.2796876000256066, "percentage": 99.95, "elapsed_time": "1 day, 7:55:05", "remaining_time": "0:00:57", "throughput": 471.45, "total_tokens": 54172192}
|
| 8196 |
+
{"current_steps": 39985, "total_steps": 40000, "loss": 3.6627, "lr": 1.9739206205682258e-11, "epoch": 1.279847640996095, "percentage": 99.96, "elapsed_time": "1 day, 7:55:07", "remaining_time": "0:00:43", "throughput": 471.5, "total_tokens": 54178880}
|
| 8197 |
+
{"current_steps": 39990, "total_steps": 40000, "loss": 4.8128, "lr": 9.329859829154685e-12, "epoch": 1.2800076819665835, "percentage": 99.98, "elapsed_time": "1 day, 7:55:09", "remaining_time": "0:00:28", "throughput": 471.55, "total_tokens": 54185392}
|
| 8198 |
+
{"current_steps": 39995, "total_steps": 40000, "loss": 3.763, "lr": 2.7758261855748148e-12, "epoch": 1.2801677229370718, "percentage": 99.99, "elapsed_time": "1 day, 7:55:11", "remaining_time": "0:00:14", "throughput": 471.6, "total_tokens": 54192000}
|
| 8199 |
+
{"current_steps": 40000, "total_steps": 40000, "loss": 4.6876, "lr": 7.710628524559838e-14, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 7:55:13", "remaining_time": "0:00:00", "throughput": 471.65, "total_tokens": 54198768}
|
| 8200 |
+
{"current_steps": 40000, "total_steps": 40000, "eval_loss": 4.496033191680908, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 8:03:19", "remaining_time": "0:00:00", "throughput": 469.66, "total_tokens": 54198768}
|
| 8201 |
+
{"current_steps": 40000, "total_steps": 40000, "epoch": 1.2803277639075603, "percentage": 100.0, "elapsed_time": "1 day, 8:03:20", "remaining_time": "0:00:00", "throughput": 469.66, "total_tokens": 54198768}
|